Current status, evidence maturity, and translational readiness of artificial intelligence in dentistry: a...

Artificial intelligence (AI) has rapidly expanded across dental research, particularly in imaging-based diagnostics and digital workflows. Despite the accelerating publication growth, the structural evolution, thematic maturity, and translational readiness of AI in dentistry remain insufficiently synthesised.

Publications related to AI in dentistry between 2015 and 2025 were retrieved from the Scopus database. Bibliometric analyses were conducted to examine annual outputs, countries, institutions, authors, journals, and keyword co-occurrence patterns. Network visualisation and clustering were performed using VOSviewer to identify research hotspots and thematic evolution. Selected evidence syntheses were evaluated using the Risk of Bias in Systematic Reviews (ROBIS) tool to assess methodological robustness and evidence maturity.

A total of 3665 publications were included. Research output demonstrated marked post-2019 acceleration, with deep learning and convolutional neural networks dominating the methodological landscape. The United States, China, and India were the most productive countries, while a core group of highly connected authors shaped collaborative structures. Keyword clustering revealed a clear thematic progression from algorithmic development and image segmentation toward diagnostic imaging applications, digital dentistry integration, and workflow optimisation. Among the 75 systematic reviews evaluated using ROBIS, 50 (66.7%) demonstrated an unclear overall risk of bias, 24 (32.0%) showed a low risk of bias, and only one (1.3%) was classified as high risk, indicating that methodological transparency and evidence synthesis have not progressed at the same pace as technological innovation.

AI research in dentistry is experiencing rapid expansion and increasing international collaboration, and continuous thematic evolution towards clinically relevant applications. However, the ROBIS assessment indicates that improvements in methodological quality and reporting transparency of evidence syntheses are still required to strengthen confidence in the current evidence base. Future studies should prioritise multicentre validation, standardised evaluation frameworks, rigorous systematic reviews, and clinically meaningful outcome measures to facilitate the safe and effective translation of AI into routine dental practice.